Research on Real-time Estimation Method of PV Output Based on Improved Transformer Model
The power estimation of each inverter of centralized photovoltaic(PV)power station can obtain the ideal output value of the PV cluster,which can provide basic data for the overall situational awareness of the whole power station and the evaluation of the real-time monitoring of the operating state of the PV system cluster.To meet the demand of PV system output estimation,a real-time PV output estimation method based on improved Transformer model is proposed.First,the system operation data and the meteorological data of the same period are collected,and then the original data is pre-processed by cleaning the data in system abnormal period and data integration.Finally,real-time estimation of PV output is realized based on the improved Transformer model and the pre-processed data set.The data of an actual centralized PV power station is used to test and analyze the proposed method.The results show that the mean absolute error(MAE)and root mean square error(RMSE)of the proposed real-time PV output estimation method based on the improved Transformer model are 0.021 and 0.186,respectively,which is better than that of the traditional methods.The feasibility and accuracy of the estimation performance of the proposed method are verified.Thus the proposed method can provide ideal output data for the evaluation of the operating state of PV power stations,and then provide basic data for intelligent PV operation and maintenance.
NETL
NSTL
万方数据
